Image Search and Annotation on a Very Large Scale
Using Deep Features and MI-File to search and annotate YFCC100M
(Yahoo Flickr Creative Commons 100M) dataset.

VEMIR
Research group

(97 millions images currently indexed)
Upload an image as query:
Chose an url as query:
Choose a random query.

Found 2460006 images similar to your query in 1567 ms (Index access Time: 104 ms, Temporary result managemet time: 796 ms, Database access time: 667 ms)

Query:

Best guessed tags:
Relevance: 15.64, Guessed tags: station
Relevance: 12.35, Guessed tags: train
Relevance: 5.76, Guessed tags: metro
Relevance: 4.16, Guessed tags: ceo
Search using images similar to your query or see more random images:


(Weight 0) Flickr->

(Weight 558) Flickr->

(Weight 578) Flickr->

(Weight 579) Flickr->

(Weight 580) Flickr->

(Weight 582) Flickr->

(Weight 586) Flickr->

(Weight 587) Flickr->

(Weight 588) Flickr->

(Weight 590) Flickr->

(Weight 592) Flickr->

(Weight 592) Flickr->

(Weight 596) Flickr->

(Weight 597) Flickr->

(Weight 601) Flickr->

(Weight 606) Flickr->

(Weight 613) Flickr->

(Weight 614) Flickr->

(Weight 616) Flickr->

(Weight 618) Flickr->
The above images are miniature versions of the original ones that come from the site www.flickr.com.
All rights are reserved to the author of the original image, which is directly available on the Flickr site through a hypertext link (surface linking).